AI · Collection
Audio Multimodal Models
Open source models with audio understanding. Tracking mostly vendor releases in the audio and text to text subclassification of multimodal.
19 models · 1 space · 1 dataset
- model stepfun-ai/Step-Audio-R1
- model Qwen/Qwen2-Audio-7B
- model Qwen/Qwen2-Audio-7B-Instruct
- model FreedomIntelligence/Soundwave
- model fixie-ai/ultravox-v0_7-glm-4_6
- model fixie-ai/ultravox-v0_5-llama-3_2-1b
- space AudioBench Leaderboard
- model Qwen/Qwen3-Omni-30B-A3B-Instruct
- model mistralai/Voxtral-Mini-3B-2507
- model moonshotai/Kimi-Audio-7B-Instruct
- model microsoft/Phi-4-multimodal-instruct
- model google/gemma-3n-E4B-it
- model Qwen/Qwen-Audio
- model google/gemma-3n-E2B
- model Qwen/Qwen-Audio-Chat
- model nvidia/audio-flamingo-2
- dataset nvidia/AudioSkills
- model nvidia/audio-flamingo-3-hf
- model nvidia/audio-flamingo-3
- model NexaAI/OmniAudio-2.6B
- model stepfun-ai/Step-Audio-Chat
Copied from Hugging Face on 7 November 2026.